© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43905
    Prev
    Next
    INDEX
    Explanations

    door or gate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fenced
    -0.11
     Ceiling
    -0.10
     Floor
    -0.10
     ÑĪÑĤ
    -0.10
     Corner
    -0.10
     foyer
    -0.09
     hallway
    -0.09
     aisle
    -0.09
    klad
    -0.09
    benh
    -0.09
    POSITIVE LOGITS
     door
    0.62
     doors
    0.53
    éŨ
    0.50
    éĸĢ
    0.47
     Door
    0.45
     двеÑĢ
    0.44
    door
    0.44
    Door
    0.42
    _door
    0.37
     gate
    0.37
    Activations Density 0.125%

    No Known Activations